Skill UI

This skill guides users through an in-depth interview process to achieve maximum project context completeness (100% "Gold Code") for their .faf file. By systematically asking questions about project goals, architecture, and technology stack, it ensures all critical context slots are filled, making the project fully structured and highly readable by AI systems.

Prevents AI style drift in legacy projects by scanning codebases for implicit conventions, resolving conflicts with users, and generating enforceable .ai-style-rules.md files with golden files, naming rules, and DONTs. Ideal for onboarding AI agents to hand-written legacy codebases or extracting unwritten coding rules.

Design, implement, review, or refactor native macOS 27 Golden Gate interfaces in SwiftUI or AppKit. Ensures apps match Apple's current macOS 27 UI kit with restrained Liquid Glass language, integrated windows, full-height sidebars, native toolbars, flat lists, and clear pane boundaries. Ideal for Figma design-to-code work and audits of boxed interfaces.

FAF Go is a guided interview skill designed to help users achieve 100% AI-readiness in their .faf project context files. It leverages Claude Code's AskUserQuestion tool to fill missing project details like goals, stack, and hosting. Users type /faf-go to start, answering questions until the Gold Code score reaches 100%. It supports single and multi-select options for fields like testing and CI/CD.